Functional Code Solvers

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 45

All topics

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Sep 30, 2026Meijia Chen, Hao Li, Zheng Lu +12Self-Evolving Agents Search Agents
Rutgers University · Independent Researcher · University of California, San Diego +3
SemOPT: Fixing Semantic Errors in LLM-based Optimization Modeling via Reward-Guided Search
Sep 29, 2026Zetong Zhou, Wentao Zhang, Jingyuan Wang +3Optimization Modeling Functional Code Solvers
School of Computer Science and Engineering, Beihang University, Beijing, China · MIIT Key Laboratory of Data and Decision Intelligence, Beihang University, Beijing, China · School of Data Science, The Chinese University of Hong Kong, Shenzhen, China +1
Q-DEQ: Discrete Solving and Quantization for Deep Equilibrium Models in Time Series Forecasting under Edge Deployment Coding Constraints
Sep 21, 2026Ruotong Yang, Hongdong Zhu, Qi Gao +3Forecasting Backbone Time Series Forecasting
Real-Time Bounded Catenary Solver for UAV Tether Modeling
Sep 16, 2026Max Beffert, Andreas ZellUnmanned Aerial Vehicles Aerodynamics
Cognitive Systems Group, University of Tübingen, Germany
ActionSplice: In-Flight Action Editing for Interactive World Models
Sep 8, 2026Pardis Taghavi, Tingyu Guo, Jonas Lossner +2Video World Models Camera-Conditioned Video Generation
Texas A&M University
Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning
Sep 1, 2026Mariia Drozdova, Aidan Sirbu, Pietro Miotti +4Functional Code Solvers Denoising Diffusion Probabilistic Model
1Google, Paradigms of Intelligence Team · School of Computer Science, McGill University · 4Mila - Quebec AI Institute +3
A Dataset for Modeling Iterative Problem-Solving
Sep 1, 2026Fagun Patel, Sang T. Truong, Duc Q. Nguyen +4Problem Solving Capability Ai-Assisted Programming Tasks
Stanford University · National University of Singapore
From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL
Aug 7, 2026Jiaqian Wang, Yutao Qi, Wenjin Hou +2Text-To-Sql Test-Time Scaling
Xidian University · Xidian University Xi’an, Shaanxi, China · Shanghai Jiao Tong University +1
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Aug 6, 2026Fanzhe Meng, Guoxin Chen, Jiale Zhao +6Agentic Benchmarks Synthetic Task
1Gaoling School of Artificial Intelligence, Renmin University of China · 2Independent Researcher · 3AweAI Team
Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
Aug 4, 2026Janis Zenkner, Tobias Sesterhenn, Tim Grams +1Functional Code Solvers Decomposition
Clausthal University of Technology Clausthal-Zellerfeld, Germany
Can LLMs Build a MaxSAT Solver from Papers? The CoreForge Experience
Jul 16, 2026Ruben MartinsSatisfiability Functional Code Solvers
Carnegie Mellon University
A Hybrid Sampling-Based Trajectory Planner with Game-Theoretic Guidance for Autonomous Racing
Jul 15, 2026Alexander Langmann, Frederico Pita de Araujo, Mattia Piccinini +1Autonomous Racing Game Theory
Professorship of Autonomous Vehicle Systems, TUM School of Engineering and Design, Technical University of Munich, 85748 Garching, Germany; Munich Institute of Robotics and Machine Intelligence (MIRMI)
Hybridizing a Grouping Metaheuristic with Reinforcement Learning for the One-Dimensional Bin Packing Problem
Jul 2, 2026Zitouni Rania, Mostefai Mounir Sofiane, Tati Youcef +3Knapsack Constraint Metaheuristics
Square Two Team – Optimization Module, École Nationale Supérieure d’Informatique (ESI), Algiers, Algeria
Structure-Oriented Randomized Neural Networks for Poisson-Nernst-Planck and Poisson-Nernst-Planck-Navier-Stokes Systems
Jun 18, 2026Yunlong Li, Fei WangReynolds-Averaged Navier-Stokes Fokker--Planck Equation
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, P.R. China. · School of Mathematics and Statistics & State Key Laboratory of Multiphase Flow in Power Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China.
Analyzing the Narration Gap in LLM-Solver Loops
Jun 17, 2026Zunchen Huang, Songgaojun DengLarge Language Model Safety LLM Reasoning Strategies
Centrum Wiskunde & Informatica, Amsterdam, The Netherlands · Eindhoven University of Technology, Eindhoven, The Netherlands
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier
Jun 10, 2026Lorenz Wolf, Connor Watts, Roger Creus Castanyer +4Functional Code Solvers Synthetic Task
Vmax · Goodfire
AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver Strategies
Jun 9, 2026Huanshuo Dong, Keyao Zhang, Hong Wang +6Neural Partial Differential Equation Solvers Classical Numerical Solver
University of Science and Technology of China · 2Zhejiang University · University of the Chinese Academy of Sciences +2
Continuous Neural Reparameterization as a Deep Geometric Prior for Robust Fixed-Chart UV Repair
Jun 8, 2026Mohammad Sadegh SalehiExtreme Ultraviolet Mesh Generation
Zero One Creative London, UK
SafeRun: Enabling Determinism in LLM Planning for Running
Jun 8, 2026Meilin Chen, Zepeng Zhai, Jiaxuan Zhao +1Large Language Model Planning Classical Planning
Xiaohongshu Inc. · Institute of Information Engineering, Chinese Academy of Sciences
Structural Grid Descriptors Predict Within-Task Solver Success on ARC-AGI
Jun 8, 2026Ayan PendharkarFunctional Code Solvers Solvers
A Study of Parallel Continuous Local Search
Jun 4, 2026Cody J Christopher, Charles GrettonLarge Neighborhood Search Satisfiability
School of Computing, Australian National University, Canberra, Australia.
Breaking Time: A Fully Gaussian Framework for Distributed and Continuous-Time SLAM
Jun 4, 2026Davide Ceriola, Simone Ferrari, Luca Di Giammarino +2Simultaneous Localization And Mapping Gaussian Primitives
Department of Computer, Control, and Management Engineering “Antonio Ruberti”, Sapienza University of Rome, Italy · University of Stuttgart, Germany
AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization
May 25, 2026Haoran Gu, Handing Wang, Yi Mei +1Functional Code Solvers Mechanics
Xidian University · Victoria University of Wellington
VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based Verification
May 24, 2026Sumaya Abdul Rahman, Seckhen Ariel Andrade Cuellar, Ghani Raissov +1Optimization Modeling Simplification
Texas A&M University at Qatar, Doha, Qatar · Carnegie Mellon University in Qatar, Doha, Qatar · Qatar Computing Research Institute, Doha, Qatar
SO-Mamba: State-Ownership Mamba for Unrolled MRI Reconstruction
May 21, 2026Pengcheng Fang, Hongli Chen, Fangfang Tang +3Magnetic Resonance Imaging Reconstruction Mamba
University of Southampton · University of Queensland · Soochow University
Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization
May 20, 2026Zhiqi Gao, Albert Ge, Alexander Berenbeim +2Optimization Modeling Supervised Finetuning
University of Wisconsin-Madison · United States Military Academy
Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning
May 20, 2026Jingfeng Zhong, Zhengxiang Liu, Zhijie Wang +1Integral Functional Code Solvers
Shanghai Jiao Tong University China
Beyond Numerical Features: CNN-Driven Algorithm Selection via Contour Plots for Continuous Black-Box Optimization
May 20, 2026Yiliang Yuan, Xiang Shi, Mustafa MisirBlack-Box Optimization Algorithm Selection
Mohamed bin Zayed University of Artificial Intelligence, Masdar City, United Arab Emirates · Duke Kunshan University, Suzhou, China
Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers
May 18, 2026Soheyl Massoudi, Gabriel Apaza, Milad Habibi +1Functional Code Solvers Offline Reinforcement Learning
ETH Zürich Zürich, Switzerland · University of Maryland College Park, MD, USA
Learning to Solve Compositional Geometry Routing Problems
May 18, 2026Mingfeng Fan, Jianan Zhou, Jiaqi Cheng +3Vehicle Routing Problem Geometry-Aware
National University of Singapore · Nanyang Technological University · Central South University
Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis
May 17, 2026Fatemeh Haji, Javier Delarosa Quiros, Peyman NajafiradFunctional Code Solvers Tree Search
Secure AI and Autonomy Lab · The University of Texas at San Antonio
Distribution-Aware Programming: Learning Specialized Solvers from Experience
May 13, 2026Saharsh Koganti, Priyadarsi Mishra, Pierfrancesco Beneventano +1Functional Code Solvers Solvers
Texas A&M University · Massachusetts Institute of Technology
ICRL: Learning to Internalize Self-Critique with Reinforcement Learning
May 13, 2026Jianbo Lin, Xiaomin Yu, Yi Xin +7Critique Offline Reinforcement Learning
Hong Kong University of Science and Technology (Guangzhou) · Nanjing University · Sun Yat-sen University +3
Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers
May 12, 2026Haoyu Wang, Yuliang Song, Tao Li +5Functional Code Solvers Solvers
University of Pennsylvania · University of Toronto · Google DeepMind +1
Evolutionary Ensemble of Agents
May 9, 2026Zongmin Yu, Liu YangFunctional Code Solvers
National University of Singapore
DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
May 7, 2026Sankarshana Venugopal, Mohammad Mostafavi, Jonghyun ChoiUnpaired Image-To-Image Translation Diffusion Bridges
Seoul National University · ECE, IPAI, ASRI in SNU
ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis
May 6, 2026Atharva Naik, Yash Mathur, Prakam +2Llm-Driven Code Synthesis Synthetic Task
Carnegie Mellon University · Independent Researcher
Strategy-Aware Optimization Modeling with Reasoning LLMs
May 4, 2026Ruiqing Zhao, Fengzhi Li, Yuan Zuo +5Optimization Modeling Functional Code Solvers
School of Computer Science and Engineering, Beihang University, Beijing, China · JIUTIAN Research, Beijing, China · MIIT Key Laboratory of Data and Decision Intelligence, Beihang University, Beijing, China
On the Expressive Power of GNNs to Solve Linear SDPs
Apr 30, 2026Chendi Qian, Christopher MorrisConvex Relaxation Graph Neural Networks
Faculty of Computer Science, RWTH Aachen University, Germany
A2DEPT: Large Language Model-Driven Automated Algorithm Design via Evolutionary Program Trees
Apr 27, 2026Bin Chen, Shouliang Zhu, Beidan Liu +4Automated Heuristic Design Functional Code Solvers
The Institute of Intelligent Computing, University of Electronic Science and Technology of China, Chengdu 611731, China · College of Systems Engineering, National University of Defense Technology, Changsha 410073, China · Academy of Military Medical Sciences, Beijing 100071, China
Similarity-based Portfolio Construction for Black-box Optimization
Apr 20, 2026Catalin-Viorel Dinu, Diederick Vermetten, Carola DoerrBlack-Box Optimization Algorithm Selection
Sorbonne Université, CNRS, LIP6
Language Models as Higher-Order Planning Formalizers
Mar 25, 2026Owen Jiang, Cassie Huang, Ashish Sabharwal +1Large Language Model Planning Classical Planning
Drexel University · Allen Institute for AI
Conservative Equilibrium Discovery in Offline Game-Theoretic Multiagent Reinforcement Learning
Feb 27, 2026Austin A. Nguyen, Michael P. WellmanEquilibrium Model-Based Reinforcement Learning
University of Michigan
LieSolver: PDE-Constrained Learning for IBVPs via Lie Symmetries
Oct 29, 2025René P. Klausen, Ivan Timofeev, Jonas Naujoks +4Partial Differential Equations Functional Code Solvers
Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany · Department of Electrical Engineering and Computer Science, Technische Universität Berlin, Germany · BIFOLD Berlin Institute for the Foundations of Learning and Data, Berlin, Germany +1
PyCSP3: Modeling Combinatorial Constrained Problems in Python
Sep 1, 2020Christophe Lecoutre, Nicolas SzczepanskiConstraint Satisfaction Combinatorial Optimization
University of Artois CRIL CNRS, UMR 8188[cs.AI] France

Sep 30, 2026, cs.CLJ/K move · Enter open · S save

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Meijia Chen, Hao Li, Zheng Lu, Hongshan Lin+11

Rutgers University · Independent Researcher · University of California, San Diego+3

Self-Evolving Agents Search Agents Iterative Co-Training Functional Code Solvers High Confidence Pseudo-Labels Frontiers+1

Open paper AskPDF arXiv

Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This closed loop introduces a failure mode we call co-cheating: the proposer and solver increasingly agree on shared errors, so internal reward improves without a matching gain in external correctness. A post-hoc audit against source evidence shows co-cheating growing more severe over successive rounds of self-evolution, with pseudo-label correctness stagnating or declining even as the in-loop training signal improves. The most direct mitigation is to verify proposals before training: we introduce multi-sample verification (MSV), which queries the same model three times with the source and three times without it to decide task admission and replace unreliable pseudo-labels. MSV partially reduces false agreement but leaves substantial residual co-cheating and costs six extra labeler generations per candidate. These limitations motivate CrossFit, our main method: it partitions the proposer's source documents into groups A and B; questions generated from A are scored by an auxiliary solver trained only on B, and vice versa. The cross-fitted agreement determines proposer reward, so a same-source pseudo-label cannot be reproduced through the feedback solver, while the original solver's update rule is unchanged. Rerunning the loop with Qwen3.5-4B and Qwen3.5-9B, MSV reduces false-agreement mass from 6.1% to 5.7% and from 8.8% to 7.2%, whereas CrossFit reduces it to 3.0% and 3.7%. Replaying identical proposals with source-excluded feedback further reduces false agreement to 0.4% and 0.1%, isolating feedback ancestry from curriculum changes. Across seven downstream search benchmarks, CrossFit improves average performance over standard coupled self-evolution by 8.8 and 8.4 points and over Search-R1 by 8.7 and 7.8 points at 4B and 9B.

Momentum

Related topics

Latest papers 45